</> Code with Papers by Syntology

Methods › General › Regularization › R1 Regularization

R1 Regularization

518 papers tagged archive 2025-07-28

Introduced by Lars Mescheder et al. in Which Training Methods for GANs do actually Converge?

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training generative adversarial networks. It penalizes the discriminator from deviating from the Nash Equilibrium via penalizing the gradient on real data alone: when the generator distribution produces the true data distribution and the discriminator is equal to 0 on the data manifold, the gradient penalty ensures that the discriminator cannot create a non-zero gradient orthogonal to the data manifold without suffering a loss in the GAN game.

This leads to the following regularization term:

R₁(ψ) = γ/2E_(p_D(x))[||∇D_ψ(x)||²]

PaperSourceSee Code · ChristophReich1996/Dirac-GAN

Papers archive 2025-07-28

30 shown of 518, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 239 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Image Generation129
Attribute63
Disentanglement48
Generative Adversarial Network36
Image Manipulation34
Face Generation33
Face Recognition25
Diversity24
Data Augmentation19
Image-to-Image Translation19
Decoder18
Face Swapping18
Transfer Learning16
Super-Resolution15
Translation15
Video Generation14
Conditional Image Generation13
Domain Adaptation13
Style Transfer12
Retrieval10

Usage over time archive 2025-07-28

Papers per year tagged with R1 Regularization: 2018 to 2025, peak 130 130 0 2018: 2 papers 2018 2019: 14 papers 2019 2020: 59 papers 2020 2021: 116 papers 2021 2022: 130 papers 2022 2023: 125 papers 2023 2024: 62 papers 2024 2025: 10 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (518 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Regularization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections